Re: [PATCH v7 0/2]: perf: reduce data loss when profiling highly parallel CPU bound workloads

From: Jiri Olsa
Date: Wed Sep 05 2018 - 07:28:58 EST


On Wed, Sep 05, 2018 at 10:16:42AM +0300, Alexey Budankov wrote:
>
> Currently in record mode the tool implements trace writing serially.
> The algorithm loops over mapped per-cpu data buffers and stores
> ready data chunks into a trace file using write() system call.
>
> At some circumstances the kernel may lack free space in a buffer
> because the other buffer's half is not yet written to disk due to
> some other buffer's data writing by the tool at the moment.
>
> Thus serial trace writing implementation may cause the kernel
> to loose profiling data and that is what observed when profiling
> highly parallel CPU bound workloads on machines with big number
> of cores.
>
> Experiment with profiling matrix multiplication code executing 128
> threads on Intel Xeon Phi (KNM) with 272 cores, like below,
> demonstrates data loss metrics value of 98%:
>
> /usr/bin/time perf record -o /tmp/perf-ser.data -a -N -B -T -R -g \
> --call-graph dwarf,1024 --user-regs=IP,SP,BP \
> --switch-events -e cycles,instructions,ref-cycles,software/period=1,name=cs,config=0x3/Duk -- \
> matrix.gcc
>
> Data loss metrics is the ratio lost_time/elapsed_time where
> lost_time is the sum of time intervals containing PERF_RECORD_LOST
> records and elapsed_time is the elapsed application run time
> under profiling.
>
> Applying asynchronous trace streaming thru Posix AIO API
> (http://man7.org/linux/man-pages/man7/aio.7.html)
> lowers data loss metrics value providing 2x improvement -
> lowering 98% loss to almost 0%.
>
> ---
> Alexey Budankov (2):
> perf util: map data buffer for preserving collected data
> perf record: enable asynchronous trace writing
>
> tools/perf/builtin-record.c | 197 +++++++++++++++++++++++++++++++++++++++++++-
> tools/perf/perf.h | 1 +
> tools/perf/util/evlist.c | 7 +-
> tools/perf/util/evlist.h | 3 +-
> tools/perf/util/mmap.c | 110 +++++++++++++++++++++----
> tools/perf/util/mmap.h | 10 ++-
> 6 files changed, 302 insertions(+), 26 deletions(-)
>
> ---
> Changes in v7:
> - implemented handling record.aio setting from perfconfig file

can't apply this version on Arnaldo's perf/core...

[jolsa@krava linux-perf]$ git am /tmp/ab/
Applying: perf util: map data buffer for preserving collected data
error: patch failed: tools/perf/util/mmap.c:166
error: tools/perf/util/mmap.c: patch does not apply

thanks,
jirka